arXiv:2607. 21325v3 Announce Type: replace-cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight.
arXiv:2607. 21325v2 Announce Type: replace-cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight.
arXiv:2607. 21325v1 Announce Type: cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight.
arXiv:2606. 03518v1 Announce Type: new Abstract: As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur.
arXiv:2606. 23768v1 Announce Type: cross Abstract: We propose cryptographic certificates of validity for agentic AI systems.
arXiv:2606. 30970v1 Announce Type: new Abstract: Autonomous AI agents increasingly perform consequential actions on behalf of human principals, including financial transactions, external communications, and enterprise workflows.
The paper examines the security challenges of delegating authority to autonomous LLM agents that act on users’ behalf. It introduces a threat model with four adversaries and eight security requirements, demonstrates that current frameworks (LangGraph, CrewAI, AutoGen, MCP) fail to meet these standards, and presents an authorization broker that blocks all identified threats with minimal overhead. The broker is shown to resist numerous attacks and limits compromised sub‑agents to their delegated tasks, and its principles are implemented in VotalAI’s LLM Shield.
arXiv:2606. 11632v1 Announce Type: cross Abstract: Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms -- such as identity and access management (IAM), policy engines, consensus protocols, and audit logs -- either enforce static, context-unaware permissions or merely record actions post-execution.
arXiv:2606. 30970v2 Announce Type: replace Abstract: Autonomous AI agents increasingly perform consequential actions on behalf of human principals, including financial transactions, external communications, and enterprise workflows.
arXiv:2608. 14074v1 Announce Type: new Abstract: AI agents increasingly act on external systems through standardized tool-calling protocols such as the Model Context Protocol (MCP), yet no infrastructure layer constrains their actions to what a principal has verifiably authorized: authorization logic lives in application code, is neither signed nor independently auditable, and the resulting logs lack evidentiary value.
arXiv:2606. 04193v1 Announce Type: cross Abstract: Current AI agent observability is structurally compromised: the entity producing the activity log is the same entity whose activity is being logged.
The paper introduces CONTINUITY, a framework that ensures secure composition of large language model (LLM) agent controls by using assume‑guarantee contracts and authenticated security contexts. It models each component with signed root grants, provenance commitments, and other mechanisms to carry security context across transitions, formalizing end‑to‑end consequence integrity. A reference verifier and fault‑injection suite demonstrate that the full configuration prevents harmful effects while completing all benign tasks and correctly escalating ambiguous cases.
arXiv:2606. 00962v1 Announce Type: cross Abstract: Foundational agent interoperability standards, notably the Agent-to-Agent (A2A) protocol and the Model Context Protocol (MCP), have advanced multi-agent system communication, and complementary identity frameworks leveraging W3C Decentralised Identifiers (DIDs) and Verifiable Credentials (VCs) provide cryptographic agent authentication.